cs.CL（2024-09-09）

📊 共 16 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗3) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct MMEvol：通过指令进化赋能多模态大语言模型，提升数据质量。 large language model multimodal
2 Doppelgänger's Watch: A Split Objective Approach to Large Language Models 提出Doppelgänger架构，分离大语言模型中的监督信号与核心能力，提升生成控制。 large language model
3 DetoxBench: Benchmarking Large Language Models for Multitask Fraud & Abuse Detection DetoxBench：用于多任务欺诈与滥用检测的大语言模型基准测试 large language model
4 Towards Democratizing Multilingual Large Language Models For Medicine Through A Two-Stage Instruction Fine-tuning Approach 提出双阶段指令微调方法以解决多语言医疗大模型的适应性问题 large language model ✅
5 Harmonic Reasoning in Large Language Models 评估大语言模型在音乐推理任务中的表现，揭示其在和声理解方面的局限性 large language model
6 Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget 在计算资源受限下，高效训练语音自监督预训练模型。 foundation model
7 Elsevier Arena: Human Evaluation of Chemistry/Biology/Health Foundational Large Language Models Elsevier Arena：化学/生物/健康领域基础大语言模型的人工评估研究 large language model
8 Seek and Solve Reasoning for Table Question Answering 提出Seek-and-Solve推理框架，提升LLM在表格问答任务中的性能 large language model chain-of-thought
9 Mathematical Formalized Problem Solving and Theorem Proving in Different Fields in Lean 4 利用大语言模型在Lean 4中实现数学问题求解与定理证明的形式化 large language model
10 CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMs CKnowEdit：首个中文知识编辑数据集，用于修正LLM中的语言、事实和逻辑错误 large language model ✅
11 Evidence from fMRI Supports a Two-Phase Abstraction Process in Language Models fMRI证据支持语言模型中存在两阶段抽象过程 large language model
12 MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation 提出MemoRAG，通过全局记忆增强检索提升长文本处理能力 large language model
13 Spatially-Aware Speaker for Vision-and-Language Navigation Instruction Generation 提出SAS：一种空间感知指令生成模型，提升视觉语言导航中指令的丰富度。 embodied AI ✅
14 Logically Consistent Language Models via Neuro-Symbolic Integration 提出基于神经符号集成的逻辑一致性语言模型，提升推理可靠性。 large language model

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
15 Multilingual Dyadic Interaction Corpus NoXi+J: Toward Understanding Asian-European Non-verbal Cultural Characteristics and their Influences on Engagement 构建多语种交互语料库NoXi+J，探究亚欧文化非语言特征对互动的影响 dyadic interaction multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
16 Towards Building a Robust Knowledge Intensive Question Answering Model with Large Language Models 提出数据增强与对比学习方法，增强LLM在知识密集型问答中对噪声的鲁棒性。 contrastive learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页